Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3500 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.8734. Min Act: -0.0000

Data Index: 897322 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.5280. Min Act: -0.0000

Data Index: 47487 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4756. Min Act: -0.0000

Data Index: 385350 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4783. Min Act: -0.0000

Data Index: 36350 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1000736 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1141059 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4525. Min Act: -0.0000

Data Index: 850578 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4077. Min Act: -0.0000

Data Index: 334912 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4519. Min Act: -0.0000

Data Index: 86927 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1024240 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1234983 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4546. Min Act: -0.0000

Data Index: 778487 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4448. Min Act: -0.0000

Data Index: 493956 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1059175 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1291716 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4197. Min Act: -0.0000

Data Index: 636452 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1293594 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4236. Min Act: -0.0000

Data Index: 942988 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.4108. Min Act: -0.0000

Data Index: 913814 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.8734. Min Range: -0.8734

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1359613 (C4 (Web Text))

Max Activating Token Index: 35